Triple
T6079899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heo Sung-tae |
E135495
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Sung-tae
Sung-tae is a Korean masculine given name commonly used in South Korea.
|
E591667
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sung-tae | Statement: [Heo Sung-tae, givenName, Sung-tae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sung-tae Context triple: [Heo Sung-tae, givenName, Sung-tae]
-
A.
Jang Deok-su
Jang Deok-su is a brutal, debt-ridden gangster who serves as one of the primary antagonists in the South Korean survival drama series "Squid Game."
-
B.
Suh Yun-bok
Suh Yun-bok was a South Korean long-distance runner best known for winning the 1947 Boston Marathon and later serving as a symbolic sports figure in Korea.
-
C.
Cho Sang-woo
Cho Sang-woo is a central character in the South Korean series "Squid Game," portrayed as a once-successful investment banker whose desperation and moral decline drive much of the show's tension and drama.
-
D.
Chung Sun-man
Chung Sun-man is a South Korean athlete best known for lighting the Olympic cauldron at the opening ceremony of the 1988 Seoul Summer Olympics.
-
E.
O Yeong-su
O Yeong-su is a veteran South Korean actor best known internationally for his acclaimed performance as the elderly contestant Oh Il-nam in the Netflix series "Squid Game."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sung-tae Triple: [Heo Sung-tae, givenName, Sung-tae]
Generated description
Sung-tae is a Korean masculine given name commonly used in South Korea.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sung-tae Target entity description: Sung-tae is a Korean masculine given name commonly used in South Korea.
-
A.
Jang Deok-su
Jang Deok-su is a brutal, debt-ridden gangster who serves as one of the primary antagonists in the South Korean survival drama series "Squid Game."
-
B.
Suh Yun-bok
Suh Yun-bok was a South Korean long-distance runner best known for winning the 1947 Boston Marathon and later serving as a symbolic sports figure in Korea.
-
C.
Cho Sang-woo
Cho Sang-woo is a central character in the South Korean series "Squid Game," portrayed as a once-successful investment banker whose desperation and moral decline drive much of the show's tension and drama.
-
D.
Chung Sun-man
Chung Sun-man is a South Korean athlete best known for lighting the Olympic cauldron at the opening ceremony of the 1988 Seoul Summer Olympics.
-
E.
O Yeong-su
O Yeong-su is a veteran South Korean actor best known internationally for his acclaimed performance as the elderly contestant Oh Il-nam in the Netflix series "Squid Game."
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c0087ad31c8190ab936e0ff28614b6 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0577209b88190afe5b1365cf6436d |
completed | March 22, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6409d48408190b2048c07272277ac |
completed | March 27, 2026, 8:32 a.m. |
| NEDg | Description generation | batch_69c6421cfa948190b62735451ede82f0 |
completed | March 27, 2026, 8:38 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c6426f194c819086fa4baffe8d237b |
completed | March 27, 2026, 8:40 a.m. |
Created at: March 22, 2026, 4:11 p.m.